Pubtator
liveBooksPubTator 3 MCP — biomedical entity search, literature search with entity highlighting, and entity-entity relations with supporting passages, from the PubTator 3 API run by NCBI / NLM (National Library of Medicine).
Tools
pubtator_find_entityResolve a gene, disease, chemical/drug, variant, species or cell-line name to its normalized PubTator 3 entity id (e.g. "BRCA1" -> @GENE_BRCA1, NCBI Gene 672; "breast cancer" -> @DISEASE_Breast_Neopla
No parameters required.
Try it
pubtator_searchSearch PubMed/PMC literature by biomedical entity and get back, for each paper, the sentence that matched with its entity mentions decoded (gene, disease, chemical, variant, species, cell line — each
No parameters required.
Try it
pubtator_relationsList the relations PubTator 3 has extracted for a gene, disease, chemical or variant — which drugs treat a disease, which genes a disease is associated with, which chemicals inhibit a gene — ranked by
No parameters required.
Try it
pubtator_relation_evidenceThe supporting passages behind one specific PubTator 3 relation — every paper whose text the model read the relation from, with the matched sentence, both entities' mentions, PMID, journal and date. G
No parameters required.
Try it
pubtator_annotationsEntity annotations for specific PubMed articles: every gene, disease, chemical, variant, species and cell-line mention in the title and abstract (or PMC full text), each normalized to NCBI Gene / MeSH
No parameters required.
Try it
Test with curl
The gateway speaks JSON-RPC 2.0 over HTTP POST. You can test any pack directly from the terminal.
curl -X POST https://gateway.pipeworx.io/pubtator/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'curl -X POST https://gateway.pipeworx.io/pubtator/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"pubtator_find_entity","arguments":{}}}'Use with the SDK
Install @pipeworx/sdk to call tools from any TypeScript/Node project.
import { Pipeworx } from '@pipeworx/sdk';
const px = new Pipeworx();
const result = await px.call("pubtator_find_entity", {});// Or ask in plain English:
const answer = await px.ask("pubtator 3 mcp — biomedical entity search, literature search with entity highlighting, and entity-entity relations with supporting passages, from the pubtator 3 api run by ncbi / nlm (national library of medicine)");